Types & classes — github.com/BICLab/SpikingBrain-7B

CodeHub MCPcopy Create free account

hub / github.com/BICLab/SpikingBrain-7B / types & classes

Types & classes101 in github.com/BICLab/SpikingBrain-7B

⨍ Functions 395◇ Types & classes 101↳ Endpoints 1

↓ 37 callersClassSpikeCountBitwiseNode

Spike count to bitwise-coded spike sequence. Emits one bit per timestep from the binary representation of the count. Supports non-negativ

W8ASpike/Int2Spike/neuron.py:193

↓ 12 callersClassQuantLinear

W8ASpike/quant_linear.py:21

↓ 10 callersClassSpikeCountBinaryLIFNode

Spike count to binary spike sequence (0/1) over T timesteps. Emits 1 each step until count reaches zero. Input x must be a non-negative i

W8ASpike/Int2Spike/neuron.py:97

↓ 10 callersClassSpikeCountTernaryLIFNode

Spike count to ternary spike sequence (-1/0/1) over T timesteps. Positive count emits +1, negative count emits -1. Input x must be an int

W8ASpike/Int2Spike/neuron.py:147

↓ 6 callersClassSpikingBrainRMSNorm

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:101

↓ 4 callersClassRMSNorm

W8ASpike/norms.py:4

↓ 4 callersClassRMSNorm

hf_7B_model/layernorm.py:626

↓ 4 callersClassRMSNorm

hf_7B_model/norms.py:4

↓ 3 callersClassMetaAttentionMetadata

vllm_hymeta/attention/meta_attention.py:129

↓ 2 callersClassGLACacheParams

vllm_hymeta/model_for_7B/gla_cache.py:9

↓ 2 callersClassSpikingBrain_VLRotaryEmbedding

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:543

↓ 1 callersClassFlashAttention

W8ASpike/window_attention.py:94

↓ 1 callersClassFlashAttention

hf_7B_model/window_attention.py:94

↓ 1 callersClassFlashAttention

vllm_hymeta/model_for_7B/modeling_gla_swa.py:133

↓ 1 callersClassGLA

hf_7B_VLM/SpikingBrain_VL/gla.py:28

↓ 1 callersClassGLACacheManager

vllm_hymeta/model_for_7B/gla_cache.py:17

↓ 1 callersClassGLAswaBlock

vllm_hymeta/model_for_7B/modeling_gla_swa.py:221

↓ 1 callersClassGLAswaGLU

vllm_hymeta/model_for_7B/modeling_gla_swa.py:96

↓ 1 callersClassGLAswaModel

vllm_hymeta/model_for_7B/modeling_gla_swa.py:309

↓ 1 callersClassGLAswaRotaryEmbedding

vllm_hymeta/model_for_7B/modeling_gla_swa.py:43

↓ 1 callersClassGLU

W8ASpike/modeling_gla_swa.py:34

↓ 1 callersClassGLU

hf_7B_model/modeling_gla_swa.py:33

↓ 1 callersClassGatedLinearAttention

W8ASpike/gla_attention.py:36

↓ 1 callersClassGatedLinearAttention

hf_7B_model/gla_attention.py:36

↓ 1 callersClassGatedLinearAttention

vllm_hymeta/model_for_7B/gla_attention.py:90

↓ 1 callersClassHybridBlock

W8ASpike/modeling_gla_swa.py:58

↓ 1 callersClassHybridBlock

hf_7B_model/modeling_gla_swa.py:57

↓ 1 callersClassHybridModel

W8ASpike/modeling_gla_swa.py:172

↓ 1 callersClassHybridModel

hf_7B_model/modeling_gla_swa.py:172

↓ 1 callersClassLowRankSequentialLinear

vllm_hymeta/model_for_7B/gla_attention.py:53

↓ 1 callersClassQuantizer

W8ASpike/quant_linear.py:52

↓ 1 callersClassRotaryEmbedding

W8ASpike/window_attention.py:23

↓ 1 callersClassRotaryEmbedding

hf_7B_model/window_attention.py:23

↓ 1 callersClassRotaryEmbedding

hf_7B_model/window_attention_sdpa.py:23

↓ 1 callersClassSpikingBrainMLP

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:604

↓ 1 callersClassSpikingBrain_VLCausalLMOutputWithPast

Base class for SpikingBrain_VL causal language model (or autoregressive) outputs. Args: loss (`torch.FloatTensor` of shape `(1,)`, *

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:1355

↓ 1 callersClassSpikingBrain_VLDecoderLayer

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:965

↓ 1 callersClassSpikingBrain_VLMLP

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:49

↓ 1 callersClassSpikingBrain_VLModel

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:1059

↓ 1 callersClassSpikingBrain_VLPatchMerger

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:121

↓ 1 callersClassSpikingBrain_VLVisionBlock

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:310

↓ 1 callersClassSpikingBrain_VL_GLA

SpikingBrain_VL flash attention module, following SpikingBrain_VL attention module. This module inherits from `SpikingBrain_VLAttention` as t

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:895

↓ 1 callersClassSpikingBrain_VL_SWA

SpikingBrain_VL flash attention module, following SpikingBrain_VL attention module. This module inherits from `SpikingBrain_VLAttention` as t

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:784

↓ 1 callersClassSpikingBrain_VisionPatchEmbed

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:63

↓ 1 callersClassSpikingBrain_VisionRotaryEmbedding

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:89

A cache used for storing hidden states produced by BoSs. It stores the states (hidden states and Key/Value/sid states) of each layer. The ex

W8ASpike/cache.py:11

A cache used for storing hidden states produced by BoSs. It stores the states (hidden states and Key/Value/sid states) of each layer. The ex

hf_7B_model/cache.py:11

ClassFastGeLUFunction

W8ASpike/activations.py:255

ClassFastGeLUFunction

hf_7B_model/activations.py:255

ClassFlashAttention

hf_7B_model/window_attention_sdpa.py:94

ClassFlashAttentionVarlenWithMetaToken

vllm_hymeta/attention/fa_kernel_metatoken.py:198

ClassFlashAttentionWithMetaToken

vllm_hymeta/attention/fa_kernel_metatoken.py:124

ClassGLAswaConfig

W8ASpike/configuration_gla_swa.py:24

ClassGLAswaConfig

hf_7B_model/configuration_gla_swa.py:24

ClassGLAswaConfig

vllm_hymeta/model_for_7B/configuration_gla_swa.py:10

ClassGLAswaForCausalLM

W8ASpike/modeling_gla_swa.py:298

ClassGLAswaForCausalLM

hf_7B_model/modeling_gla_swa.py:296

ClassGLAswaForCausalLM

vllm_hymeta/model_for_7B/modeling_gla_swa.py:502

ClassGLAswaGPTQ

hf_7B_model/gla_swa_gptq.py:8

ClassGeLUFunction

W8ASpike/activations.py:216

ClassGeLUFunction

hf_7B_model/activations.py:216

hf_7B_model/layernorm.py:578

ClassGroupNormLinear

hf_7B_model/layernorm.py:847

ClassHybridPreTrainedModel

W8ASpike/modeling_gla_swa.py:129

ClassHybridPreTrainedModel

hf_7B_model/modeling_gla_swa.py:128

ClassHymetaCudaPlatform

Platform for HYMETA Cache on CUDA.

vllm_hymeta/platform.py:10

hf_7B_model/layernorm.py:536

ClassLayerNormFn

hf_7B_model/layernorm.py:383

ClassLayerNormLinear

hf_7B_model/layernorm.py:802

ClassLayerNormLinearFn

hf_7B_model/layernorm.py:668

ClassLogSigmoidFunction

W8ASpike/activations.py:131

ClassLogSigmoidFunction

hf_7B_model/activations.py:131

ClassMetaAttentionBackend

vllm_hymeta/attention/meta_attention.py:53

ClassMetaAttentionImpl

If the input tensors contain prompt tokens, the layout is as follows: |<--------------- num_prefill_tokens ----------------->| |<--prefi

vllm_hymeta/attention/meta_attention.py:611

ClassMetaAttentionMetadataBuilder

vllm_hymeta/attention/meta_attention.py:411

ClassMyFusedRecurrentFunction

vllm_hymeta/model_for_7B/my_fused_recurrent.py:83

ClassRMSNormLinear

hf_7B_model/layernorm.py:898

ClassRecurrentStateHolder

hf_7B_VLM/SpikingBrain_VL/utils.py:6

ClassSigmoidFunction

W8ASpike/activations.py:28

ClassSigmoidFunction

hf_7B_model/activations.py:28

ClassSpikeCountBaseLIFNode

W8ASpike/Int2Spike/neuron.py:8

ClassSpikingBrain_VLAttention

Multi-headed attention from 'Attention Is All You Need' paper. Modified to use sliding window attention: Longformer and "Generating Long Sequ

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:677

ClassSpikingBrain_VLConfig

This is the configuration class to store the configuration of a `SpikingBrain_VLModel`.

hf_7B_VLM/SpikingBrain_VL/configuration_spikingbrain_vl.py:44

ClassSpikingBrain_VLForConditionalGeneration

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:1469

ClassSpikingBrain_VLPreTrainedModel

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:358

ClassSpikingBrain_VLProcessor

hf_7B_VLM/SpikingBrain_VL/processing_spikingbrain_vl.py:23

ClassSpikingBrain_VLProcessorKwargs

hf_7B_VLM/SpikingBrain_VL/processing_spikingbrain_vl.py:13

ClassSpikingBrain_VLVideosProcessorKwargs

hf_7B_VLM/SpikingBrain_VL/processing_spikingbrain_vl.py:9

ClassSpikingBrain_VLVisionAttention

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:210

ClassSpikingBrain_VLVisionConfig

This is the configuration class to store the configuration of a `SpikingBrain_VLVisionModel`.

hf_7B_VLM/SpikingBrain_VL/configuration_spikingbrain_vl.py:3

ClassSpikingBrain_VLVisionFlashAttention2

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:149

ClassSpikingBrain_VLVisionSdpaAttention

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:260

ClassSpikingBrain_VisionTransformerPretrainedModel

hf_7B_VLM/SpikingBrain_VL/modeling_spikingbrain_vl.py:381

ClassSquaredReLUFunction

W8ASpike/activations.py:288

ClassSquaredReLUFunction

hf_7B_model/activations.py:288

ClassSwiGLUFunction

r""" Swish-Gated Linear Unit (SwiGLU) function. .. math:: \text{SwiGLU}(x, y) = swish(x) * y = \frac{x}{1 + \exp(-x)} * y

W8ASpike/activations.py:378

ClassSwiGLUFunction

r""" Swish-Gated Linear Unit (SwiGLU) function. .. math:: \text{SwiGLU}(x, y) = swish(x) * y = \frac{x}{1 + \exp(-x)} * y

hf_7B_model/activations.py:378

ClassSwiGLULinearFunction

r""" Swish-Gated Linear Unit (SwiGLU) function followed by a linear transformation. .. math:: \text{SwiGLULinear}(x, y, W, b) = (swis

W8ASpike/activations.py:397

ClassSwiGLULinearFunction

r""" Swish-Gated Linear Unit (SwiGLU) function followed by a linear transformation. .. math:: \text{SwiGLULinear}(x, y, W, b) = (swis

hf_7B_model/activations.py:397

ClassSwishFunction

W8ASpike/activations.py:171

next →1–100 of 101, ranked by callers